Skip to main content

CostLens MCP

FinOps MCP Server for BigQuery — Cost estimation, query optimization, and safe execution.

Installation

# Via pip
pip install costlens-mcp

# Via uvx (recommended)
uvx costlens-mcp --project YOUR_PROJECT

Quick Start

# If you've run `gcloud auth application-default login`
costlens-mcp --project my-project

# With service account
costlens-mcp --project my-project --key-file /path/to/key.json

# Enable query execution (with cost limit)
costlens-mcp --project my-project --allow-execute --max-cost 5.0

Tools

Tool Description
estimate_query_cost Precise cost via BigQuery dry-run
list_tables Tables with sizes
describe_table Schema + partitions
execute_query Cost-gated execution
get_optimizations Structured suggestions

MCP Configuration

{
  "mcpServers": {
    "costlens": {
      "command": "uvx",
      "args": ["costlens-mcp", "--project", "YOUR_PROJECT"]
    }
  }
}

License

MIT

Metadata

Release files for costlens-mcp 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for costlens-mcp 1.0.0
File Size Uploaded Provenance
costlens_mcp-1.0.0.tar.gz 31.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for costlens-mcp 1.0.0
File Interpreter ABI Platform
costlens_mcp-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 48.0 kB

Release files / costlens_mcp-1.0.0.tar.gz

Download URL costlens_mcp-1.0.0.tar.gz
Size 31.6 kB
Tags Source
SHA-256 checksum
How to use checksums
a49893e69402c3e05525ab2feeb379f71ab4f978fe7c1ec95006586a6f2645e6
BLAKE2b-256 checksum
How to use checksums
9dc55dd7ea7108954cee999137826e8d184b3284f2e5e93c2848b947ee253f8f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.2

Release files / costlens_mcp-1.0.0-py3-none-any.whl

Download URL costlens_mcp-1.0.0-py3-none-any.whl
Size 16.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
dad55378e28d10042d669b1e80bf88f4ffac5b894c5d4bbcd082ddfc51ed3c71
BLAKE2b-256 checksum
How to use checksums
492e5903dc94d482b25b85d985973983638d633f01b6ceef3a4eecb9d3915e43
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.2

Security for costlens-mcp 1.0.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page